Landing method, system and equipment of unmanned aerial vehicle and medium

Abstract

The invention discloses a landing method, system and equipment of an unmanned aerial vehicle and a medium, and relates to the technical field of unmanned aerial vehicles, and the method comprises the steps: obtaining a video image and flight information of the unmanned aerial vehicle in real time, carrying out the landing point recognition of the video image based on a preset landing point template image, obtaining a landing point position, and carrying out the safety evaluation of the flight information; and determining safety evaluation data corresponding to the unmanned aerial vehicle, and controlling the unmanned aerial vehicle to land to the landing point position according to the safety evaluation data and the flight information. The technical problems that in the prior art, landing control is mainly performed on the unmanned aerial vehicle based on a landing method of reinforcement learning, but in actual flight, the unmanned aerial vehicle faces external interference of different working conditions, so that the unmanned aerial vehicle cannot land according to a preset track, and the operation safety of the unmanned aerial vehicle is reduced are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicles, and in particular to a landing method, system, equipment and medium for unmanned aerial vehicles. Background Art

[0002] With the rapid development of drone technology, drones are increasingly used in various fields. However, drones face many challenges during landing, especially in complex environments (such as cities, forests, and mountains). How to achieve safe landing of drones has become a key issue that needs to be solved urgently.

[0003] At present, the existing technology mainly controls the landing of UAVs based on the landing method of reinforcement learning. However, in actual flight, UAVs will face external interference under different working conditions, which will cause the UAV to be unable to land according to the preset trajectory, reducing the safety of UAV operation. Summary of the invention

[0004] The present invention provides a landing method, system, equipment and medium for a drone, which solves the technical problem that the landing method of the prior art is mainly based on reinforcement learning to control the landing of the drone, but in actual flight, the drone will face external interference under different working conditions, resulting in the drone being unable to land according to a preset trajectory, thereby reducing the safety of the drone operation.

[0005] A first aspect of the present invention provides a method for landing an unmanned aerial vehicle, comprising:

[0006] Acquire the video image and flight information of the drone in real time, and identify the landing point of the video image based on a preset landing point template image to obtain the landing point position;

[0007] Performing a safety assessment on the flight information to determine safety assessment data corresponding to the UAV;

[0008] The UAV is controlled to land at the landing point according to the safety assessment data and the flight information.

[0009] Optionally, the step of performing landing point recognition on the video image based on a preset landing point template image to obtain the landing point position includes:

[0010] Dividing the video image into a plurality of coordinate feature images;

[0011] Calculating the similarity between the preset landing point template image and each of the coordinate feature images respectively;

[0012] The greatest similarity is selected from each of the similarities as the target similarity, and the coordinate position associated with the target similarity is determined as the landing point position.

[0013] Optionally, the flight information includes a position of the drone, an attitude angle, and positions of multiple obstacles, and the step of performing a safety assessment on the flight information to determine safety assessment data corresponding to the drone includes:

[0014] Calculate the distance between the position of the drone and each obstacle respectively, and select the minimum distance value from each distance value as the target distance value;

[0015] The target distance value is compared with a preset distance threshold to obtain a safety factor;

[0016] Performing difference processing on the attitude angle and a preset expected attitude angle to obtain a first difference;

[0017] Multiplying the absolute value of the first difference by a preset adjustment coefficient to obtain a first multiplied value;

[0018] Adding a preset stability coefficient to the first multiplication value to obtain a first sum value;

[0019] The stability coefficient is ratio-processed with the first sum value to obtain an attitude stability coefficient, and the attitude stability coefficient and the safety factor are determined as safety assessment data corresponding to the UAV.

[0020] Optionally, the step of controlling the drone to land at the landing point according to the safety assessment data and the flight information includes:

[0021] Determining whether the safety factor is less than a preset safety threshold;

[0022] If the safety factor is less than the safety threshold, controlling the UAV to land at the landing point according to the flight information using a preset first control strategy;

[0023] If the safety factor is greater than or equal to the safety threshold, determining whether the posture stability factor is greater than a preset stability threshold;

[0024] If the attitude stability coefficient is less than or equal to the stability threshold, controlling the UAV to land at the landing point according to the flight information using a preset second control strategy;

[0025] If the attitude stability coefficient is greater than the stability threshold, the UAV is controlled to land at the landing point according to the flight information using a preset third control strategy.

[0026] Optionally, the step of controlling the UAV to land at the landing point according to the flight information using a preset first control strategy includes:

[0027] Input the wind speed data of the flight information and the speed data of the drone into a preset environmental interference function to obtain wind resistance data;

[0028] Generate a first landing path according to the position of the drone and the position of the landing point;

[0029] The detection distance of the flight information is multiplied by a preset first optimization coefficient to obtain a first correction distance;

[0030] Determining a first endpoint position of the drone based on the first calibration distance and the first landing path;

[0031] Inputting the first terminal position, the wind resistance data and the flight information into a pre-trained first path optimization model to obtain a first optimized path and a first adjustment parameter;

[0032] Determining whether the first end point position is the landing point position;

[0033] If the first terminal position is the landing point position, controlling the UAV to fly to the landing point position along the first optimized path according to the first adjustment parameter;

[0034] If the first terminal position is not the landing point position, the UAV is controlled to fly along the first optimized path to the first terminal position according to the first adjustment parameter, and the step of obtaining the video image and flight information of the UAV in real time is jumped to be executed.

[0035] Optionally, the step of controlling the UAV to land at the landing point according to the flight information using a preset second control strategy includes:

[0036] Inputting the flight information into a preset PID control model to obtain a second adjustment parameter;

[0037] Generate a second landing path according to the position of the drone and the position of the landing point;

[0038] The detection data of the flight information is multiplied by a preset second optimization coefficient to obtain a second correction distance;

[0039] Determining a second endpoint position of the drone based on the second correction distance and the second landing path;

[0040] Inputting the second terminal position, the second adjustment parameter and the flight information into a pre-trained second path optimization model to obtain a second optimized path;

[0041] Determining whether the second end point position is the landing point position;

[0042] If the second terminal position is the landing point position, controlling the UAV to fly to the landing point position along the second optimized path according to the second adjustment parameter;

[0043] If the second terminal position is not the landing point position, the UAV is controlled to fly along the second optimized path to the second terminal position according to the second adjustment parameter, and the step of obtaining the video image and flight information of the UAV in real time is jumped to be executed.

[0044] Optionally, the step of controlling the UAV to land at the landing point according to the flight information using a preset third control strategy includes:

[0045] Generate a third landing path according to the position of the drone and the position of the landing point;

[0046] Optimizing the third landing path based on a preset local path optimization algorithm and the flight information to obtain a third optimized path;

[0047] Controlling the UAV to fly to the landing point along the third optimized path, and obtaining the flight time of the UAV in real time;

[0048] Determining whether the flight time is greater than a preset time threshold;

[0049] When the flight time is greater than the time threshold, the process jumps to executing the step of acquiring the video image and flight information of the drone in real time.

[0050] A second aspect of the present invention provides a landing system for an unmanned aerial vehicle, comprising:

[0051] The acquisition module is used to obtain the video image and flight information of the UAV in real time, and identify the landing point of the video image based on the preset landing point template image to obtain the landing point position;

[0052] An evaluation module, used to perform a safety evaluation on the flight information and determine safety evaluation data corresponding to the UAV;

[0053] A control module is used to control the UAV to land at the landing point according to the safety assessment data and the flight information.

[0054] A third aspect of the present invention provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the drone landing method as described in any one of the above items.

[0055] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed, the method for landing a drone as described in any one of the above items is implemented.

[0056] It can be seen from the above technical solutions that the present invention has the following advantages:

[0057] The present invention obtains the video image and flight information of the UAV in real time, identifies the landing point of the video image, obtains the landing point position, performs a safety assessment on the flight information, determines the safety assessment data corresponding to the UAV, and controls the UAV to land at the landing point position according to the safety assessment data and flight information. It overcomes the technical problem that the landing method of the prior art is mainly based on reinforcement learning to control the landing of the UAV, but in actual flight, the UAV will face external interference in different working conditions, resulting in the UAV being unable to land according to the preset trajectory, thereby reducing the safety of the UAV operation. Compared with the traditional landing method, the present invention obtains the flight information of the UAV in real time, and controls the UAV to land at the landing point position according to the flight information and safety assessment data, thereby realizing dynamic adjustment of the UAV during the landing process and improving the safety of the UAV operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0059] Figure 1 A flowchart of a method for landing a drone provided in Embodiment 1 of the present invention;

[0060] Figure 2 A flowchart of a method for landing a drone provided in Embodiment 2 of the present invention;

[0061] Figure 3 A structural block diagram of a landing system for a drone provided in Embodiment 3 of the present invention;

[0062] Figure 4 This is a structural block diagram of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0063] An embodiment of the present invention provides a landing method for a drone, which is used to solve the technical problem that the existing technology mainly uses a landing method based on reinforcement learning to control the landing of a drone, but in actual flight, the drone will face external interference under different working conditions, resulting in the drone being unable to land according to a preset trajectory, thereby reducing the safety of the drone operation.

[0064] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0065] See also Figure 1 , Figure 1 A flowchart of a method for landing a drone provided in Embodiment 1 of the present invention.

[0066] The present invention provides a method for landing an unmanned aerial vehicle, comprising:

[0067] Step 101: acquiring video images and flight information of the drone in real time, and performing landing point recognition on the video images based on a preset landing point template image to obtain the landing point position;

[0068] Flight information refers to the status information and environmental information of the drone. The status information includes the drone's position, flight speed, attitude angle deviation and angular velocity, and the environmental information includes the drone's battery level and the locations of multiple obstacles.

[0069] In the embodiment of the present invention, the video image and flight information of the drone are acquired in real time, and the video image is preprocessed to obtain the preprocessed video image, and the video image is divided into a plurality of coordinate feature images. The preset landing point model image is compared with each coordinate feature image one by one to obtain the landing point position.

[0070] Step 102: Perform a safety assessment on the flight information to determine the safety assessment data corresponding to the UAV;

[0071] In the embodiment of the present invention, the distance values ​​between the position of the drone and the positions of each obstacle are calculated respectively, and the minimum distance value is selected from each distance value as the target distance value, and the target distance value is compared with the preset distance threshold value to obtain the safety factor, and the attitude angle and the preset expected attitude angle are input into the preset attitude stability function to obtain the attitude stability coefficient. The safety factor and the attitude stability coefficient are used as the safety assessment data corresponding to the drone.

[0072] It should be noted that the attitude stabilization function is specifically:

[0073]

[0074] in, is the attitude stability coefficient, is the adjustment factor, is the attitude angle, is the desired attitude angle.

[0075] Step 103: Control the UAV to land at the landing point according to the safety assessment data and flight information.

[0076] In an embodiment of the present invention, it is determined whether the safety factor is less than a preset safety threshold. If the safety factor is less than the safety threshold, the UAV is controlled to land to the landing point according to the preset first control strategy based on the flight information. If the safety factor is greater than or equal to the safety threshold, it is determined whether the attitude stability coefficient is greater than the preset stability threshold. If the attitude stability coefficient is less than or equal to the stability threshold, the UAV is controlled to land to the landing point according to the flight information according to the preset second control strategy. If the attitude stability coefficient is greater than the stability threshold, the UAV is controlled to land to the landing point according to the preset third control strategy based on the flight information.

[0077] In an embodiment of the present invention, the video image and flight information of the UAV are acquired in real time, and the landing point is identified on the video image to obtain the landing point position, and the flight information is safety assessed to determine the safety assessment data corresponding to the UAV, thereby controlling the UAV to land at the landing point position according to the safety assessment data and flight information. This overcomes the technical problem that the landing method of the prior art is mainly based on reinforcement learning to control the landing of the UAV, but in actual flight, the UAV will face external interference under different working conditions, resulting in the UAV being unable to land according to the preset trajectory, thereby reducing the safety of the UAV operation. Compared with the traditional landing method, the present invention acquires the flight information of the UAV in real time, and controls the UAV to land at the landing point position according to the flight information and safety assessment data, thereby realizing dynamic adjustment of the UAV during the landing process and improving the safety of the UAV operation.

[0078] See also Figure 2 , Figure 2 A flowchart of a method for landing a drone provided in Embodiment 2 of the present invention.

[0079] The present invention provides a method for landing an unmanned aerial vehicle, comprising:

[0080] Step 201: acquiring video images and flight information of the drone in real time, and dividing the video images into a plurality of coordinate feature images;

[0081] In the embodiment of the present invention, the video image and flight information of the UAV are acquired in real time, and the video image is segmented into a plurality of coordinate feature images.

[0082] Step 202, respectively calculating the similarity between the preset landing point template image and each coordinate feature image;

[0083] In the embodiment of the present invention, the similarity between the preset landing point template image and each coordinate feature image is calculated by comparing the pixel values ​​between the preset landing point template image and each coordinate feature image.

[0084] Step 203: Select the greatest similarity from each similarity as the target similarity, and determine the coordinate position associated with the target similarity as the landing point position.

[0085] In the embodiment of the present invention, the greatest similarity is selected from various similarities as the target similarity, and the coordinate position associated with the target similarity is marked as the landing point position.

[0086] Step 204: Perform a safety assessment on the flight information to determine the safety assessment data corresponding to the UAV;

[0087] Furthermore, the flight information includes the position of the drone, the attitude angle, and the positions of multiple obstacles. Step 204 includes the following sub-steps:

[0088] S11, respectively calculating the distance values ​​between the position of the UAV and the position of each obstacle, and selecting the minimum distance value from each distance value as the target distance value;

[0089] In the embodiment of the present invention, the distance values ​​between the position of the drone and the position of each obstacle are calculated respectively, and the minimum distance value is selected from all the distance values ​​as the target distance value.

[0090] S12, performing ratio processing on the target distance value and the preset distance threshold to obtain a safety factor;

[0091] In the embodiment of the present invention, the target distance value and the preset distance threshold are input into a preset safety function to obtain a safety factor.

[0092] It should be noted that the security function is specifically:

[0093]

[0094] in, is the safety factor, is the target distance value, is the distance threshold.

[0095] S13, performing difference processing on the attitude angle and the preset expected attitude angle to obtain a first difference;

[0096] In the embodiment of the present invention, the difference between the attitude angle and the preset expected attitude angle is calculated to obtain a first difference.

[0097] S14, multiplying the absolute value of the first difference by a preset adjustment coefficient to obtain a first multiplied value;

[0098] In the embodiment of the present invention, a multiplication value between the absolute value of the first difference and a preset adjustment coefficient is calculated to obtain a first multiplication value.

[0099] S15, adding the preset stability coefficient and the first multiplication value to obtain a first sum value;

[0100] In the embodiment of the present invention, a sum of a preset stability coefficient and a first multiplication value is calculated to obtain a first sum.

[0101] S16. Perform ratio processing on the stability coefficient and the first sum value to obtain an attitude stability coefficient, and determine the attitude stability coefficient and the safety factor as safety assessment data corresponding to the UAV.

[0102] In the embodiment of the present invention, the stability coefficient is ratio-processed with the first sum value to obtain the attitude stability coefficient, and the attitude stability coefficient and the safety factor are used as the safety assessment data corresponding to the UAV.

[0103] Step 205: Control the UAV to land at the landing point according to the safety assessment data and flight information.

[0104] Further, step 205 includes the following sub-steps:

[0105] S21, determining whether the safety factor is less than a preset safety threshold;

[0106] In the embodiment of the present invention, it is determined whether the safety factor is less than 1.

[0107] S22, if the safety factor is less than the safety threshold, controlling the UAV to land at the landing point according to the flight information using a preset first control strategy;

[0108] Further, S22 includes the following sub-steps:

[0109] S221, inputting the wind speed data of the flight information and the speed data of the UAV into a preset environmental interference function to obtain wind resistance data;

[0110] In an embodiment of the present invention, if the safety factor is less than 1, the wind speed data and the drone speed data of the flight information are input into a preset environmental interference function to obtain wind resistance data. The wind speed data includes the horizontal axis wind speed (i.e., the wind speed in the x-axis direction), the longitudinal axis wind speed (i.e., the wind speed in the y-axis direction), and the depth axis wind speed (i.e., the wind speed in the z-axis direction), and the drone speed data includes the horizontal axis drone speed (i.e., the x-axis drone speed), the longitudinal axis drone speed (i.e., the y-axis drone speed), and the depth axis drone speed (i.e., the z-axis drone speed).

[0111] It should be noted that the wind group data includes horizontal axis wind resistance, vertical axis wind resistance and depth axis wind resistance.

[0112] It should be noted that the environmental interference function is specifically:

[0113]

[0114] in, is the horizontal axis wind resistance, is the longitudinal wind resistance, is the deep axis wind resistance, is the horizontal axis drag coefficient, is the longitudinal axis drag coefficient, is the drag coefficient of the depth axis, is the air density, is the windward area of ​​the UAV, is the horizontal axis wind speed, is the vertical axis wind speed, is the depth axis wind speed, is the horizontal axis drone speed, is the vertical axis UAV speed, is the speed of the drone along the depth axis.

[0115] S222, generating a first landing path according to the position of the UAV and the position of the landing point;

[0116] In an embodiment of the present invention, a first landing path is generated according to the position of the drone and the position of the landing point, wherein the first landing path is a straight line path from the position of the drone to the landing position (regardless of whether it passes through obstacles).

[0117] S223, multiplying the detection distance of the flight information by a preset first optimization coefficient to obtain a first correction distance;

[0118] In the embodiment of the present invention, the multiplication value between the detection distance of the flight information and 0.6 is calculated to obtain the first calibration distance.

[0119] S224, determining a first terminal position of the UAV based on the first calibration distance and the first landing path;

[0120] In the embodiment of the present invention, A1. The first calibration distance is used as the selected target distance. A2. According to the selected target distance, the point on the first landing path that is farthest from the current distance of the drone is selected as the first terminal position. A3. When the first terminal position coincides with the obstacle position, the selected target distance is adjusted according to the preset gradient value. A4. Step A2 is re-executed until the selected first terminal position does not coincide with the obstacle position.

[0121] S225, inputting the first terminal position, wind resistance data and flight information into a pre-trained first path optimization model to obtain a first optimized path and a first adjustment parameter;

[0122] In the embodiment of the present invention, the first terminal position, wind resistance data and flight information are used as inputs of the first path optimization model to obtain the first optimized path and the first adjustment parameters.

[0123] It should be noted that the training process of the first path optimization model is specifically as follows:

[0124] B1. Obtain training landing data, and build a simulation environment for the UAV landing mission based on the training landing data, where the simulation environment includes the landing area, obstacles, wind resistance, etc.

[0125] B2. Use the training landing data to train the initial first path optimization model to obtain training landing path data.

[0126] B3. Calculate the reward function value of the training landing data based on the training landing path data.

[0127] The specific reward function is:

[0128]

[0129] in, is the reward value at time t, is the position of the drone at time t, is the target landing position, is the distance between the drone and the obstacle.

[0130] B4. When the reward function value is less than or equal to the preset standard reward function value, the adaptive optimization algorithm is used to adjust the network parameters of the initial first path optimization model, and the process jumps to execute A2 until the reward function value is greater than the standard reward function value.

[0131] B5. When the reward function value is greater than the standard reward function value, a first path optimization model is generated.

[0132] It is worth mentioning that the first path optimization model is a CNN neural network.

[0133] S226, determining whether the first end point is a landing point;

[0134] S227: If the first terminal position is the landing point position, control the UAV to fly to the landing point position along the first optimized path according to the first adjustment parameter;

[0135] In an embodiment of the present invention, it is determined whether the first terminal position is a landing point position. When the first terminal position is a landing point position, the UAV is controlled to fly to the landing point position along the first optimized path according to the first adjustment parameter.

[0136] S228: If the first terminal position is not the landing point, the UAV is controlled to fly along the first optimized path to the first terminal position according to the first adjustment parameter, and the process jumps to the step of acquiring the video image and flight information of the UAV in real time.

[0137] In the embodiment of the present invention, when the first terminal position is not the landing point position, the UAV is controlled to fly to the first terminal position along the first optimized path according to the first adjustment parameter, and the process jumps to execute step 201.

[0138] S23, if the safety factor is greater than or equal to the safety threshold, determining whether the posture stability factor is greater than a preset stability threshold;

[0139] In the embodiment of the present invention, when the safety factor is greater than or equal to 1, it is determined whether the posture stability coefficient is greater than a preset stability threshold.

[0140] S24, if the attitude stability coefficient is less than or equal to the stability threshold, controlling the UAV to land at the landing point according to the flight information using a preset second control strategy;

[0141] Further, S24 includes the following sub-steps:

[0142] S241, inputting the flight information into a preset PID control model to obtain a second adjustment parameter;

[0143] In an embodiment of the present invention, if the attitude stability coefficient is less than or equal to the stability threshold, the flight information is input into a preset PID control model to obtain a second adjustment parameter, wherein the second adjustment parameter includes an adjustment speed, an adjustment attitude angle, an angular velocity, and the like.

[0144] S242, generating a second landing path according to the position of the UAV and the position of the landing point;

[0145] In an embodiment of the present invention, a second landing path is generated according to the position of the drone and the position of the landing point, wherein the second landing path is a straight line path from the position of the drone to the landing position (regardless of whether it passes through obstacles).

[0146] S243, multiplying the detection data of the flight information by a preset second optimization coefficient to obtain a second correction distance;

[0147] In the embodiment of the present invention, the multiplication value between the detection data of the flight information and 0.8 is calculated to obtain the second correction distance.

[0148] S244, determining a second terminal position of the UAV based on the second correction distance and the second landing path;

[0149] In the embodiment of the present invention, C1. The second calibration distance is used as the selected target distance. C2. According to the selected target distance, the point on the second landing path that is farthest from the current distance of the drone is selected as the second terminal position. C3. When the second terminal position coincides with the obstacle position, the selected target distance is adjusted according to the preset gradient value. C4. Step C2 is re-executed until the selected second terminal position does not coincide with the obstacle position.

[0150] S245, inputting the second terminal position, the second adjustment parameter and the flight information into a pre-trained second path optimization model to obtain a second optimized path;

[0151] In the embodiment of the present invention, the second terminal position, the second adjustment parameter and the flight information are used as inputs of a pre-trained second path optimization model to obtain a second optimized path.

[0152] It should be noted that the training process of the second path optimization model is similar to the training process of the first path optimization model, the difference being that when the second path optimization model is trained, the simulation environment does not include wind resistance.

[0153] S246, determining whether the second end point is a landing point;

[0154] S247, if the second terminal position is the landing point position, controlling the UAV to fly to the landing point position along the second optimized path according to the second adjustment parameter;

[0155] In an embodiment of the present invention, it is determined whether the second terminal position is the landing point position. When the second terminal position is the landing point position, the UAV is controlled to fly to the landing point position along the second optimized path according to the second adjustment parameter.

[0156] S248: If the second terminal position is not the landing point, the UAV is controlled to fly along the second optimized path to the second terminal position according to the second adjustment parameter, and the process jumps to the step of acquiring the video image and flight information of the UAV in real time.

[0157] In the embodiment of the present invention, when the second terminal position is not the landing point position, the UAV is controlled to fly to the second terminal position along the second optimized path according to the second adjustment parameter, and the process jumps to execute step 201.

[0158] S25. If the attitude stability coefficient is greater than the stability threshold, the UAV is controlled to land at the landing point according to the flight information using a preset third control strategy.

[0159] Further, S25 includes the following sub-steps:

[0160] S251, generating a third landing path according to the position of the UAV and the position of the landing point;

[0161] In an embodiment of the present invention, a third landing path is generated according to the position of the drone and the position of the landing point, wherein the third landing path is a straight line path from the position of the drone to the landing position (regardless of whether it passes through obstacles).

[0162] S252, optimizing the third landing path based on a preset local path optimization algorithm and flight information to obtain a third optimized path;

[0163] In an embodiment of the present invention, the third landing path is optimized based on a preset local path optimization algorithm and flight information to obtain a third optimized path, wherein the local path optimization algorithm includes but is not limited to a dynamic window method (DWA), an artificial potential field method (APF), a rapidly exploring random tree (RRT) series, a probabilistic roadmap (PRM), a model predictive control (MPC), an APF+RRT / MPC* method, and a DRL+traditional planning.

[0164] S253, controlling the UAV to fly to the landing point along the third optimized path, and obtaining the flight time of the UAV in real time;

[0165] S254, determining whether the flight time is greater than a preset time threshold;

[0166] In an embodiment of the present invention, the UAV is controlled to fly along the third optimized path to the landing point, and the flight time of the UAV is obtained in real time to determine whether the flight time is greater than a preset time threshold.

[0167] S255: When the flight time is greater than the time threshold, jump to the step of acquiring the video image and flight information of the drone in real time.

[0168] In the embodiment of the present invention, when the flight time is greater than the time threshold, the process jumps to step 201 .

[0169] In an embodiment of the present invention, the video image and flight information of the UAV are acquired in real time, and the landing point is identified on the video image to obtain the landing point position, and the flight information is safety assessed to determine the safety assessment data corresponding to the UAV, thereby controlling the UAV to land at the landing point position according to the safety assessment data and flight information. This overcomes the technical problem that the landing method of the prior art is mainly based on reinforcement learning to control the landing of the UAV, but in actual flight, the UAV will face external interference under different working conditions, resulting in the UAV being unable to land according to the preset trajectory, thereby reducing the safety of the UAV operation. Compared with the traditional landing method, the present invention acquires the flight information of the UAV in real time, and controls the UAV to land at the landing point position according to the flight information and safety assessment data, thereby realizing dynamic adjustment of the UAV during the landing process and improving the safety of the UAV operation.

[0170] See also Figure 3 , Figure 3 This is a structural block diagram of a landing system for an unmanned aerial vehicle provided in Embodiment 3 of the present invention.

[0171] The present invention provides a landing system for an unmanned aerial vehicle, comprising:

[0172] The acquisition module 301 is used to obtain the video image and flight information of the drone in real time, and identify the landing point of the video image based on the preset landing point template image to obtain the landing point position;

[0173] An evaluation module 302 is used to perform a safety evaluation on the flight information and determine the safety evaluation data corresponding to the UAV;

[0174] The control module 303 is used to control the UAV to land at the landing point according to the safety assessment data and flight information.

[0175] Furthermore, the acquisition module 301 includes:

[0176] A segmentation submodule, used for dividing the video image into a plurality of coordinate feature images;

[0177] A matching submodule, used to calculate the similarity between the preset landing point template image and each coordinate feature image;

[0178] The first selection submodule is used to select the greatest similarity from various similarities as the target similarity, and determine the coordinate position associated with the target similarity as the landing point position.

[0179] Furthermore, the flight information includes the position, attitude angle and positions of multiple obstacles of the drone. The evaluation module 302 includes:

[0180] The second selection submodule is used to calculate the distance values ​​between the position of the drone and the position of each obstacle, and select the minimum distance value from each distance value as the target distance value;

[0181] The safety assessment submodule is used to compare the target distance value with the preset distance threshold to obtain a safety factor;

[0182] The posture evaluation submodule is used to perform difference processing between the posture angle and the preset expected posture angle to obtain a first difference;

[0183] The absolute value of the first difference is multiplied by a preset adjustment coefficient to obtain a first multiplied value;

[0184] Adding the preset stability coefficient and the first multiplication value to obtain a first sum value;

[0185] The stability coefficient is ratio-processed with the first sum value to obtain the attitude stability coefficient, and the attitude stability coefficient and the safety factor are determined as the safety assessment data corresponding to the UAV.

[0186] Furthermore, the control module 303 includes:

[0187] The first analysis submodule is used to determine whether the safety factor is less than a preset safety threshold;

[0188] A first control submodule, configured to control the UAV to land at a landing point according to a preset first control strategy based on flight information if the safety factor is less than a safety threshold;

[0189] The second analysis submodule is used to determine whether the posture stability coefficient is greater than a preset stability threshold if the safety factor is greater than or equal to the safety threshold;

[0190] A second control submodule is used to control the UAV to land at a landing point according to a preset second control strategy based on the flight information if the attitude stability coefficient is less than or equal to the stability threshold;

[0191] The third control submodule is used to control the UAV to land at the landing point according to the preset third control strategy based on the flight information if the attitude stability coefficient is greater than the stability threshold.

[0192] Furthermore, the first control submodule includes:

[0193] A wind resistance analysis unit, used to input the wind speed data of the flight information and the speed data of the UAV into a preset environmental interference function to obtain wind resistance data;

[0194] A first planning unit, configured to generate a first landing path according to the position of the UAV and the position of the landing point;

[0195] The detection distance of the flight information is multiplied by a preset first optimization coefficient to obtain a first correction distance;

[0196] Determining a first endpoint position of the drone based on the first calibration distance and the first landing path;

[0197] A first optimization unit, configured to input the first terminal position, wind resistance data, and flight information into a pre-trained first path optimization model to obtain a first optimized path and a first adjustment parameter;

[0198] A first analysis unit, used to determine whether the first end point position is a landing point position;

[0199] If the first terminal position is the landing point position, the UAV is controlled to fly along the first optimized path to the landing point position according to the first adjustment parameter;

[0200] If the first terminal position is not the landing point position, the UAV is controlled to fly along the first optimized path to the first terminal position according to the first adjustment parameter, and the step of obtaining the video image and flight information of the UAV in real time is jumped to be executed.

[0201] Furthermore, the second control submodule includes:

[0202] A second analysis unit is used to input the flight information into a preset PID control model to obtain a second adjustment parameter;

[0203] A second planning unit is used to generate a second landing path according to the position of the UAV and the position of the landing point;

[0204] The detection data of the flight information is multiplied by a preset second optimization coefficient to obtain a second correction distance;

[0205] Determining a second endpoint position of the UAV based on the second corrected distance and the second landing path;

[0206] A second optimization unit, used for inputting the second terminal position, the second adjustment parameter and the flight information into a pre-trained second path optimization model to obtain a second optimized path;

[0207] A third analysis unit is used to determine whether the second end point position is a landing point position;

[0208] If the second terminal position is the landing point position, the UAV is controlled to fly along the second optimized path to the landing point position according to the second adjustment parameter;

[0209] If the second terminal position is not the landing point, the UAV is controlled to fly to the second terminal position along the second optimized path according to the second adjustment parameter, and the step of obtaining the video image and flight information of the UAV in real time is jumped to be executed.

[0210] Furthermore, the third control submodule includes:

[0211] A third planning unit, used for generating a third landing path according to the position of the UAV and the position of the landing point;

[0212] Optimizing the third landing path based on a preset local path optimization algorithm and flight information to obtain a third optimized path;

[0213] A control unit, used to control the UAV to fly along the third optimized path to the landing point and obtain the flight time of the UAV in real time;

[0214] A fourth analysis unit, used to determine whether the flight time is greater than a preset time threshold;

[0215] When the flight time is greater than the time threshold, the process jumps to the step of acquiring the video image and flight information of the drone in real time.

[0216] See also Figure 4 , Figure 4 This is a structural block diagram of an electronic device provided in Embodiment 4 of the present invention.

[0217] An electronic device according to an embodiment of the present invention includes: a memory 401 and a processor 402, wherein the memory 402 stores a computer program; when the computer program is executed by the processor 402, the processor 402 executes the landing method of the drone according to any of the above embodiments.

[0218] The memory 401 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read-only memory), an EPROM, a hard disk or a ROM. The memory 401 has a storage space 403 for a program code 413 for executing any method step in the above method. For example, the storage space 403 for the program code may include individual program codes 413 for implementing the various steps in the above method, respectively. These program codes may be read from or written to one or more computer program products. These computer program products include program code carriers such as a hard disk, a compact disk (CD), a memory card or a floppy disk. The program code may be compressed, for example, in an appropriate form. When these codes are run by a computing and processing device, the computing and processing device is caused to execute the various steps in the above-described method.

[0219] Embodiment 5 of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, a landing method for a drone as in any of the above embodiments is implemented.

[0220] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0221] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0222] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0223] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0224] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0225] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for landing a drone, characterized in that: include: Acquire the video image and flight information of the drone in real time, and identify the landing point of the video image based on a preset landing point template image to obtain the landing point position; Performing a safety assessment on the flight information to determine safety assessment data corresponding to the UAV; The UAV is controlled to land at the landing point according to the safety assessment data and the flight information.

2. The method for landing a drone according to claim 1, characterized in that: The step of performing landing point recognition on the video image based on a preset landing point template image to obtain the landing point position includes: Dividing the video image into a plurality of coordinate feature images; Calculating the similarity between the preset landing point template image and each of the coordinate feature images respectively; The greatest similarity is selected from each of the similarities as the target similarity, and the coordinate position associated with the target similarity is determined as the landing point position.

3. The method for landing a drone according to claim 1, characterized in that: The flight information includes the position, attitude angle and positions of multiple obstacles of the drone. The step of performing safety assessment on the flight information and determining the safety assessment data corresponding to the drone includes: Calculate the distance between the position of the drone and each obstacle respectively, and select the minimum distance value from each distance value as the target distance value; The target distance value is compared with a preset distance threshold to obtain a safety factor; Performing difference processing on the attitude angle and a preset expected attitude angle to obtain a first difference; Multiplying the absolute value of the first difference by a preset adjustment coefficient to obtain a first multiplied value; Adding a preset stability coefficient to the first multiplication value to obtain a first sum value; The stability coefficient is ratio-processed with the first sum value to obtain an attitude stability coefficient, and the attitude stability coefficient and the safety factor are determined as safety assessment data corresponding to the UAV.

4. The method for landing a drone according to claim 3, characterized in that: The step of controlling the drone to land at the landing point according to the safety assessment data and the flight information comprises: Determining whether the safety factor is less than a preset safety threshold; If the safety factor is less than the safety threshold, controlling the UAV to land at the landing point according to the flight information using a preset first control strategy; If the safety factor is greater than or equal to the safety threshold, determining whether the posture stability factor is greater than a preset stability threshold; If the attitude stability coefficient is less than or equal to the stability threshold, controlling the UAV to land at the landing point according to the flight information using a preset second control strategy; If the attitude stability coefficient is greater than the stability threshold, the UAV is controlled to land at the landing point according to the flight information using a preset third control strategy.

5. The method for landing a drone according to claim 4, characterized in that: The step of controlling the UAV to land at the landing point according to the flight information using a preset first control strategy comprises: Input the wind speed data of the flight information and the speed data of the drone into a preset environmental interference function to obtain wind resistance data; Generate a first landing path according to the position of the drone and the position of the landing point; The detection distance of the flight information is multiplied by a preset first optimization coefficient to obtain a first correction distance; Determining a first endpoint position of the drone based on the first calibration distance and the first landing path; Inputting the first terminal position, the wind resistance data and the flight information into a pre-trained first path optimization model to obtain a first optimized path and a first adjustment parameter; Determining whether the first end point position is the landing point position; If the first terminal position is the landing point position, controlling the UAV to fly to the landing point position along the first optimized path according to the first adjustment parameter; If the first terminal position is not the landing point position, the UAV is controlled to fly along the first optimized path to the first terminal position according to the first adjustment parameter, and the step of obtaining the video image and flight information of the UAV in real time is jumped to be executed.

6. The method for landing a drone according to claim 4, characterized in that: The step of controlling the UAV to land at the landing point according to the flight information using a preset second control strategy includes: Inputting the flight information into a preset PID control model to obtain a second adjustment parameter; Generate a second landing path according to the position of the drone and the position of the landing point; The detection data of the flight information is multiplied by a preset second optimization coefficient to obtain a second correction distance; Determining a second endpoint position of the drone based on the second correction distance and the second landing path; Inputting the second terminal position, the second adjustment parameter and the flight information into a pre-trained second path optimization model to obtain a second optimized path; Determining whether the second end point position is the landing point position; If the second terminal position is the landing point position, controlling the UAV to fly to the landing point position along the second optimized path according to the second adjustment parameter; If the second terminal position is not the landing point position, the UAV is controlled to fly along the second optimized path to the second terminal position according to the second adjustment parameter, and the step of obtaining the video image and flight information of the UAV in real time is jumped to be executed.

7. The method for landing a drone according to claim 4, characterized in that: The step of controlling the UAV to land at the landing point according to the flight information using a preset third control strategy includes: Generate a third landing path according to the position of the drone and the position of the landing point; Optimizing the third landing path based on a preset local path optimization algorithm and the flight information to obtain a third optimized path; Controlling the UAV to fly to the landing point along the third optimized path, and obtaining the flight time of the UAV in real time; Determining whether the flight time is greater than a preset time threshold; When the flight time is greater than the time threshold, the process jumps to executing the step of acquiring the video image and flight information of the drone in real time.

8. A landing system for an unmanned aerial vehicle, characterized in that: include: The acquisition module is used to obtain the video image and flight information of the UAV in real time, and identify the landing point of the video image based on the preset landing point template image to obtain the landing point position; An evaluation module, used to perform a safety evaluation on the flight information and determine safety evaluation data corresponding to the UAV; A control module is used to control the UAV to land at the landing point according to the safety assessment data and the flight information.

9. An electronic device, characterized in that: It includes a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the landing method of the drone as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed, the landing method of the drone as described in any one of claims 1-7 is implemented.

Images